Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to research methodology and results evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enumi
    -0.41
     luck
    -0.40
     TK
    -0.39
     CTR
    -0.39
     love
    -0.39
     Mira
    -0.38
     dignity
    -0.38
     TB
    -0.38
     DC
    -0.37
     Solo
    -0.37
    POSITIVE LOGITS
     propOrder
    0.63
    CloseOperation
    0.63
    Попис
    0.62
     мәкал
    0.61
    jsxFileName
    0.61
     ſind
    0.60
    qrstuvwxyz
    0.53
    transQ
    0.51
     disambiguazione
    0.50
     Verſ
    0.50
    Act Density 2.719%

    No Known Activations